ATDMNet: Multi-Head Agent Attention and Top-k Dynamic Mask for Camouflaged Object Detection

Camouflaged object detection (COD) encounters substantial difficulties owing to the visual resemblance between targets and their environments, together with discrepancies in multiscale representation of features. Current methodologies confront obstacles with feature distraction, modeling far-reachin...

Full description

Saved in:
Bibliographic Details
Published inSensors (Basel, Switzerland) Vol. 25; no. 10; p. 3001
Main Authors Fu, Rui, Li, Yuehui, Chen, Chih-Cheng, Duan, Yile, Yao, Pengjian, Zhou, Kaixin
Format Journal Article
LanguageEnglish
Published Switzerland MDPI AG 09.05.2025
MDPI
Subjects
Accuracy
Analysis
camouflaged object detection
Computational linguistics
Computer vision
digital images
feature extraction
Language processing
Localization
Natural language interfaces
Neural networks
self-attention network
Semantics
visualization
China
self-attention network
camouflaged object detection
visualization
feature extraction
digital images
Online AccessGet full text

Cover

More Information
Summary:Camouflaged object detection (COD) encounters substantial difficulties owing to the visual resemblance between targets and their environments, together with discrepancies in multiscale representation of features. Current methodologies confront obstacles with feature distraction, modeling far-reaching dependencies, fusing multiple-scale details, and extracting boundary specifics. Consequently, we propose ATDMNet, an amalgamated architecture combining CNN and transformer within a numerous phases feature extraction framework. ATDMNet employs Res2Net as the foundational encoder and incorporates two essential components: multi-head agent attention (MHA) and top-k dynamic mask (TDM). MHA improves local feature sensitivity and long-range dependency modeling by incorporating agent nodes and positional biases, whereas TDM boosts attention with top-k operations and multiscale dynamic methods. The decoding phase utilizes bilinear upsampling and sophisticated semantic guidance to enhance low-level characteristics, hence ensuring precise segmentation. Enhanced performance is achieved by deep supervision and a hybrid loss function. Experiments applying COD datasets (NC4K, COD10K, CAMO) demonstrate that ATDMNet establishes a new benchmark in both precision and efficiency.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1424-8220
1424-8220
DOI:10.3390/s25103001